Skip to main content
Publications lead hero image abstract pattern


Publication Date

Manuscript Submission Deadline

Special Issue

Call for Articles

We are witnessing the emergence of billions of IoT devices fuelled by tremendous leaps in computing paradigms spanning clients, edge and the cloud, as well as the ultra low-latency and Gbps connectivity offered by 5G networks. It is estimated that IoT devices will generate 90 Zettabytes of data at the network edge by 2025 (IDC Data Age 2025 Whitepaper). The Industry 4.0 revolution is one of the major drivers for this large-scale adoption of IoT and is taking place rapidly, transforming a wide range of markets including manufacturing, energy, agriculture, transportation and logistics. For example, in smart manufacturing, predictive maintenance for minimizing downtime, location tracking for inventory and automation are some key areas that can boost yield and decrease the time-to-market. Similarly, in energy, smart metering and detecting defects in oil/gas extraction stations as well as in the extracted matter are leading to significant improvements in operational and capital expenditures.

Access to abundant multi-modal data in such industrial use cases means that Machine Learning and Artificial Intelligence (AI) will play an integral role in the analysis and understanding of the data, the improvement of operational efficiency and product quality, as well as the reduction of down time by several orders of magnitude. Successfully implementing an ML-based solution for Industrial IoT (IIoT) involves many aspects, including but not limited to: (i) adequate infrastructure placement for timely and accurate collection of data from multiple sensors; (ii) aggregation of data at gateways/cloud; (iii) development and adoption of advanced AI algorithms; and (iv) hosting ML-related tasks at the edge for the purpose of reducing the network load. Industry 4.0 will change forever factories as we know them, with distributed manufacturing and on-demand personalized products reaching a wide scale.

This Special Issue (SI) solicits high-quality articles in the area of end-to-end ML for IIoT as described above. To this end, academic and industrial researchers and practitioners are invited to submit original work in this area leveraging machine learning/deep learning, data collection and analysis, online and unsupervised algorithms, robotics and cloud computing. Authors are also encouraged to demonstrate the suitability of their proposed ML-based IIoT solutions developed to complement real-world large-scale industrial systems and small-scale laboratory testbeds.

Manuscripts should: a) describe in depth and/or breadth real-world multi-disciplinary ML-/AI-based IIoT deployments that align with this special issue as described above; b) present newly gained experiences in resolving challenges for adopting ML at all of the device, edge and cloud levels; c) develop and share best practices, vision realizations and lessons learned from such experiences/new deployments; and d) establish guiding principles for technical, operational and business successes. Articles should be general, independent of technical or business specialty, and intended for an audience consisting of all members of the IoT community.

Topics of interest include, but are not limited to:

  1. Edge, Distributed and Collaborative AI for Industrial IoT
  2. Machine Learning for Predictive Analytics including Maintenance
  3. Systems Aspects of the Data Collection Pipeline
  4. AI-driven Private Networks for IIoT
  5. Large-scale AI integration in Industrial Environments
  6. Applications of AI for Control Functions and Operations
  7. Applications of Computer Vision in IIoT
  8. Unsupervised, Self-supervised Learning and Online/Offline Reinforcement Learning for IIoT
  9. Representation Learning for IIoT
  10. Graph-Based Modeling and Learning for IIoT
  11. Transfer Learning for IIoT including real-world implementations
  12. Testbed and performance evaluation studies of AI/ML techniques for IIoT
  13. Computing architectures supporting AI/ML techniques for IIoT
  14. AI-/ML-driven networking and wireless communications for IIoT
  15. Sustainability and Carbon Neutrality with enlightened IIoT

Submission Guidelines

Manuscripts should conform to the IEEE Internet of Things Magazine standard format as indicated in the Information for Authors section of the Article Submission Guidelines. All manuscripts to be considered for publication must be submitted by the deadline through the magazine’s Manuscript Central site. Select “March 2022/An End-to-end Machine Learning Perspective on Industrial IoT” from the drop-down menu of Topic/Series titles.

Important Dates

Manuscripts Due: 30 October 2021
First Decision Date: 15 December 2021
Revisions Due: 15 January 2022
Final Decision Date: 31 January 2022
Camera-ready Files Due: 15 February 2022
Guest Editorial/Column: 22 February 2022
Expected Publication Date: March 2022

Guest Editors

Rita Wouhaybi (Lead Guest Editor)
Intel Corporation, USA

Ravikumar Balakrishnan (Corresponding Guest Editor)
Intel Corporation, USA

Anirudh Badam
Microsoft, USA

Shadi Noghabi
Microsoft, USA

Ahmad Beirami
Facebook AI, USA

Shugong Xu
Shanghai Institute for Advanced Comm & Data Science, China

Navid NaderiAlizadeh
University of Pennsylvania, USA

Marco Di Felice
University of Bologna, Italy